segformer-b0-finetuned-segments-sidewalk-3

This model is a fine-tuned version of nvidia/mit-b0 on the segments/sidewalk-semantic dataset. It achieves the following results on the evaluation set:

• Loss: 0.5669
• Mean Iou: 0.3190
• Mean Accuracy: 0.3821
• Overall Accuracy: 0.8574
• Accuracy Unlabeled: nan
• Accuracy Flat-road: 0.9199
• Accuracy Flat-sidewalk: 0.9566
• Accuracy Flat-crosswalk: 0.5855
• Accuracy Flat-cyclinglane: 0.8187
• Accuracy Flat-parkingdriveway: 0.4712
• Accuracy Flat-railtrack: nan
• Accuracy Flat-curb: 0.5293
• Accuracy Human-person: 0.7962
• Accuracy Human-rider: 0.0
• Accuracy Vehicle-car: 0.9245
• Accuracy Vehicle-truck: 0.0
• Accuracy Vehicle-bus: 0.0
• Accuracy Vehicle-tramtrain: nan
• Accuracy Vehicle-motorcycle: 0.0
• Accuracy Vehicle-bicycle: 0.5123
• Accuracy Vehicle-caravan: 0.0
• Accuracy Vehicle-cartrailer: 0.0
• Accuracy Construction-building: 0.8912
• Accuracy Construction-door: 0.0
• Accuracy Construction-wall: 0.5405
• Accuracy Construction-fenceguardrail: 0.3863
• Accuracy Construction-bridge: 0.0
• Accuracy Construction-tunnel: nan
• Accuracy Construction-stairs: 0.0
• Accuracy Object-pole: 0.4414
• Accuracy Object-trafficsign: 0.0
• Accuracy Object-trafficlight: 0.0
• Accuracy Nature-vegetation: 0.9331
• Accuracy Nature-terrain: 0.8636
• Accuracy Sky: 0.9713
• Accuracy Void-ground: 0.0000
• Accuracy Void-dynamic: 0.0
• Accuracy Void-static: 0.3037
• Accuracy Void-unclear: 0.0
• Iou Unlabeled: nan
• Iou Flat-road: 0.7635
• Iou Flat-sidewalk: 0.8715
• Iou Flat-crosswalk: 0.5513
• Iou Flat-cyclinglane: 0.7441
• Iou Flat-parkingdriveway: 0.3799
• Iou Flat-railtrack: nan
• Iou Flat-curb: 0.4143
• Iou Human-person: 0.5353
• Iou Human-rider: 0.0
• Iou Vehicle-car: 0.8080
• Iou Vehicle-truck: 0.0
• Iou Vehicle-bus: 0.0
• Iou Vehicle-tramtrain: nan
• Iou Vehicle-motorcycle: 0.0
• Iou Vehicle-bicycle: 0.3478
• Iou Vehicle-caravan: 0.0
• Iou Vehicle-cartrailer: 0.0
• Iou Construction-building: 0.7370
• Iou Construction-door: 0.0
• Iou Construction-wall: 0.3749
• Iou Construction-fenceguardrail: 0.3203
• Iou Construction-bridge: 0.0
• Iou Construction-tunnel: nan
• Iou Construction-stairs: 0.0
• Iou Object-pole: 0.3284
• Iou Object-trafficsign: 0.0
• Iou Object-trafficlight: 0.0
• Iou Nature-vegetation: 0.8586
• Iou Nature-terrain: 0.7283
• Iou Sky: 0.9243
• Iou Void-ground: 0.0000
• Iou Void-dynamic: 0.0
• Iou Void-static: 0.2014
• Iou Void-unclear: 0.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 6e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Unlabeled	Accuracy Flat-road	Accuracy Flat-sidewalk	Accuracy Flat-crosswalk	Accuracy Flat-cyclinglane	Accuracy Flat-parkingdriveway	Accuracy Flat-railtrack	Accuracy Flat-curb	Accuracy Human-person	Accuracy Human-rider	Accuracy Vehicle-car	Accuracy Vehicle-truck	Accuracy Vehicle-bus	Accuracy Vehicle-tramtrain	Accuracy Vehicle-motorcycle	Accuracy Vehicle-bicycle	Accuracy Vehicle-caravan	Accuracy Vehicle-cartrailer	Accuracy Construction-building	Accuracy Construction-door	Accuracy Construction-wall	Accuracy Construction-fenceguardrail	Accuracy Construction-bridge	Accuracy Construction-tunnel	Accuracy Construction-stairs	Accuracy Object-pole	Accuracy Object-trafficsign	Accuracy Object-trafficlight	Accuracy Nature-vegetation	Accuracy Nature-terrain	Accuracy Sky	Accuracy Void-ground	Accuracy Void-dynamic	Accuracy Void-static	Accuracy Void-unclear	Iou Unlabeled	Iou Flat-road	Iou Flat-sidewalk	Iou Flat-crosswalk	Iou Flat-cyclinglane	Iou Flat-parkingdriveway	Iou Flat-railtrack	Iou Flat-curb	Iou Human-person	Iou Human-rider	Iou Vehicle-car	Iou Vehicle-truck	Iou Vehicle-bus	Iou Vehicle-tramtrain	Iou Vehicle-motorcycle	Iou Vehicle-bicycle	Iou Vehicle-caravan	Iou Vehicle-cartrailer	Iou Construction-building	Iou Construction-door	Iou Construction-wall	Iou Construction-fenceguardrail	Iou Construction-bridge	Iou Construction-tunnel	Iou Construction-stairs	Iou Object-pole	Iou Object-trafficsign	Iou Object-trafficlight	Iou Nature-vegetation	Iou Nature-terrain	Iou Sky	Iou Void-ground	Iou Void-dynamic	Iou Void-static	Iou Void-unclear
1.2409	1.0	200	1.2471	0.1570	0.2044	0.7356	nan	0.8032	0.9526	0.0	0.3067	0.0000	nan	0.0	0.0	0.0	0.9054	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8352	0.0	0.0007	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9434	0.6803	0.9090	0.0	0.0	0.0	0.0	nan	0.5173	0.7510	0.0	0.2997	0.0000	nan	0.0	0.0	0.0	0.5787	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.5852	0.0	0.0007	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7164	0.5939	0.8246	0.0	0.0	0.0	0.0
1.1443	2.0	400	0.9634	0.1732	0.2195	0.7607	nan	0.8231	0.9651	0.0	0.5125	0.0159	nan	0.0005	0.0	0.0	0.9316	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.8419	0.0	0.0476	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9224	0.8029	0.9413	0.0	0.0	0.0	0.0	nan	0.5515	0.7650	0.0	0.4662	0.0157	nan	0.0005	0.0	0.0	0.6181	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6102	0.0	0.0440	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.7835	0.6602	0.8541	0.0	0.0	0.0	0.0
0.8805	3.0	600	0.8309	0.1963	0.2429	0.7804	nan	0.8858	0.9438	0.0	0.5258	0.2765	nan	0.2373	0.0	0.0	0.8852	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9159	0.0	0.1947	0.0000	0.0	nan	0.0	0.0004	0.0	0.0	0.9174	0.8250	0.9226	0.0	0.0	0.0	0.0	nan	0.5450	0.8189	0.0	0.4853	0.2291	nan	0.1953	0.0	0.0	0.7014	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6219	0.0	0.1442	0.0000	0.0	nan	0.0	0.0004	0.0	0.0	0.7977	0.6821	0.8641	0.0	0.0	0.0	0.0
0.5657	4.0	800	0.7312	0.2177	0.2662	0.8045	nan	0.8296	0.9595	0.0118	0.7076	0.3690	nan	0.3339	0.0056	0.0	0.9077	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.9036	0.0	0.4576	0.0102	0.0	nan	0.0	0.0242	0.0	0.0	0.9308	0.8451	0.9532	0.0	0.0	0.0040	0.0	nan	0.6207	0.8228	0.0118	0.6313	0.2862	nan	0.2661	0.0055	0.0	0.7236	0.0	0.0	nan	0.0	0.0	0.0	0.0	0.6724	0.0	0.2571	0.0102	0.0	nan	0.0	0.0240	0.0	0.0	0.8220	0.7057	0.8862	0.0	0.0	0.0039	0.0
0.7813	5.0	1000	0.6767	0.2476	0.2950	0.8246	nan	0.8929	0.9575	0.3536	0.7434	0.3652	nan	0.3249	0.1722	0.0	0.9367	0.0	0.0	nan	0.0	0.0191	0.0	0.0	0.9078	0.0	0.4430	0.1157	0.0	nan	0.0	0.1126	0.0	0.0	0.9239	0.8638	0.9630	0.0	0.0	0.0504	0.0	nan	0.6867	0.8456	0.3488	0.6502	0.3199	nan	0.2679	0.1656	0.0	0.7052	0.0	0.0	nan	0.0	0.0189	0.0	0.0	0.6895	0.0	0.2999	0.1092	0.0	nan	0.0	0.1055	0.0	0.0	0.8259	0.6999	0.8927	0.0	0.0	0.0447	0.0
0.7435	6.0	1200	0.6344	0.2760	0.3279	0.8357	nan	0.9055	0.9490	0.5276	0.7616	0.4465	nan	0.4423	0.6483	0.0	0.9186	0.0	0.0	nan	0.0	0.0494	0.0	0.0	0.9033	0.0	0.4453	0.1511	0.0	nan	0.0	0.2289	0.0	0.0	0.9545	0.7769	0.9534	0.0	0.0	0.1015	0.0	nan	0.7209	0.8647	0.5022	0.6648	0.3552	nan	0.3400	0.4843	0.0	0.7524	0.0	0.0	nan	0.0	0.0493	0.0	0.0	0.7024	0.0	0.3020	0.1429	0.0	nan	0.0	0.1947	0.0	0.0	0.8107	0.6785	0.9045	0.0	0.0	0.0868	0.0
0.669	7.0	1400	0.6076	0.2955	0.3517	0.8449	nan	0.9070	0.9577	0.6665	0.7372	0.4645	nan	0.4506	0.7302	0.0	0.9348	0.0	0.0	nan	0.0	0.1936	0.0	0.0	0.8990	0.0	0.5097	0.2575	0.0	nan	0.0	0.2668	0.0	0.0	0.9282	0.8178	0.9587	0.0	0.0	0.2242	0.0	nan	0.7469	0.8615	0.5876	0.6676	0.3702	nan	0.3492	0.5076	0.0	0.7583	0.0	0.0	nan	0.0	0.1678	0.0	0.0	0.7182	0.0	0.3413	0.2286	0.0	nan	0.0	0.2275	0.0	0.0	0.8431	0.7139	0.9073	0.0	0.0	0.1654	0.0
0.4628	8.0	1600	0.6011	0.2977	0.3549	0.8429	nan	0.8884	0.9527	0.5578	0.7506	0.4890	nan	0.4638	0.7406	0.0	0.9319	0.0	0.0	nan	0.0	0.3178	0.0	0.0	0.9010	0.0	0.4809	0.3284	0.0	nan	0.0	0.2448	0.0	0.0	0.9241	0.8614	0.9616	0.0	0.0	0.2085	0.0	nan	0.7334	0.8587	0.5336	0.6751	0.3767	nan	0.3613	0.5230	0.0	0.7468	0.0	0.0	nan	0.0	0.2516	0.0	0.0	0.7101	0.0	0.3365	0.2738	0.0	nan	0.0	0.2136	0.0	0.0	0.8427	0.7254	0.9085	0.0	0.0	0.1589	0.0
1.3419	9.0	1800	0.5904	0.3029	0.3709	0.8462	nan	0.9057	0.9510	0.6361	0.7788	0.4788	nan	0.4900	0.8107	0.0	0.9469	0.0	0.0	nan	0.0	0.4336	0.0	0.0	0.8507	0.0	0.5368	0.3238	0.0	nan	0.0	0.2916	0.0	0.0	0.9233	0.8610	0.9637	0.0	0.0	0.3155	0.0	nan	0.7455	0.8668	0.5717	0.7045	0.3669	nan	0.3797	0.4684	0.0	0.7556	0.0	0.0	nan	0.0	0.2745	0.0	0.0	0.7145	0.0	0.3328	0.2865	0.0	nan	0.0	0.2461	0.0	0.0	0.8508	0.7261	0.9126	0.0	0.0	0.1879	0.0
0.5734	10.0	2000	0.5937	0.3046	0.3620	0.8455	nan	0.8903	0.9576	0.4874	0.7802	0.4436	nan	0.5076	0.7526	0.0	0.9252	0.0	0.0	nan	0.0	0.3795	0.0	0.0	0.8933	0.0	0.5108	0.3422	0.0	nan	0.0	0.3250	0.0	0.0	0.9355	0.8361	0.9634	0.0	0.0	0.2901	0.0	nan	0.7358	0.8573	0.4710	0.6988	0.3621	nan	0.3880	0.5318	0.0	0.7827	0.0	0.0	nan	0.0	0.3118	0.0	0.0	0.7178	0.0	0.3584	0.2906	0.0	nan	0.0	0.2654	0.0	0.0	0.8469	0.7203	0.9165	0.0	0.0	0.1862	0.0
0.3721	11.0	2200	0.5782	0.3079	0.3675	0.8503	nan	0.9192	0.9460	0.5240	0.8234	0.4822	nan	0.5023	0.7689	0.0	0.8965	0.0	0.0	nan	0.0	0.4271	0.0	0.0	0.9199	0.0	0.5107	0.3373	0.0	nan	0.0	0.4079	0.0	0.0	0.9468	0.8152	0.9624	0.0	0.0	0.2037	0.0	nan	0.7498	0.8668	0.5037	0.7028	0.3740	nan	0.3838	0.5157	0.0	0.7946	0.0	0.0	nan	0.0	0.3237	0.0	0.0	0.7340	0.0	0.3586	0.2842	0.0	nan	0.0	0.3043	0.0	0.0	0.8469	0.7219	0.9174	0.0	0.0	0.1618	0.0
0.5698	12.0	2400	0.5601	0.3147	0.3796	0.8547	nan	0.9163	0.9502	0.6118	0.8102	0.5160	nan	0.4905	0.7891	0.0	0.9196	0.0	0.0	nan	0.0	0.4718	0.0	0.0	0.8898	0.0	0.5471	0.4070	0.0	nan	0.0	0.4158	0.0	0.0	0.9320	0.8523	0.9700	0.0	0.0	0.2787	0.0	nan	0.7765	0.8684	0.5737	0.7307	0.3860	nan	0.3917	0.5271	0.0	0.7968	0.0	0.0	nan	0.0	0.2862	0.0	0.0	0.7351	0.0	0.3521	0.3301	0.0	nan	0.0	0.3084	0.0	0.0	0.8525	0.7310	0.9171	0.0	0.0	0.1921	0.0
0.4268	13.0	2600	0.5706	0.3144	0.3758	0.8546	nan	0.9149	0.9584	0.5832	0.8127	0.4595	nan	0.5052	0.7785	0.0	0.9385	0.0	0.0	nan	0.0	0.4538	0.0	0.0	0.8974	0.0	0.5469	0.3876	0.0	nan	0.0	0.3971	0.0	0.0	0.9269	0.8398	0.9644	0.0	0.0	0.2853	0.0	nan	0.7632	0.8670	0.5583	0.7345	0.3711	nan	0.3931	0.5330	0.0	0.7866	0.0	0.0	nan	0.0	0.3082	0.0	0.0	0.7333	0.0	0.3694	0.3199	0.0	nan	0.0	0.3094	0.0	0.0	0.8565	0.7309	0.9212	0.0	0.0	0.1913	0.0
0.3612	14.0	2800	0.5615	0.3182	0.3797	0.8587	nan	0.9143	0.9554	0.6527	0.8256	0.4717	nan	0.5467	0.7521	0.0	0.9229	0.0	0.0	nan	0.0	0.4951	0.0	0.0	0.9226	0.0	0.5236	0.3953	0.0	nan	0.0	0.4144	0.0	0.0	0.9329	0.8347	0.9637	0.0	0.0	0.2473	0.0	nan	0.7803	0.8714	0.5854	0.7509	0.3843	nan	0.4085	0.5363	0.0	0.7994	0.0	0.0	nan	0.0	0.3118	0.0	0.0	0.7381	0.0	0.3688	0.3250	0.0	nan	0.0	0.3138	0.0	0.0	0.8547	0.7242	0.9233	0.0	0.0	0.1865	0.0
0.2714	15.0	3000	0.5687	0.3165	0.3819	0.8557	nan	0.9102	0.9546	0.5390	0.8252	0.4823	nan	0.5408	0.8170	0.0	0.9223	0.0	0.0	nan	0.0	0.5004	0.0	0.0	0.8929	0.0	0.5402	0.4228	0.0	nan	0.0	0.4218	0.0	0.0	0.9324	0.8585	0.9674	0.0	0.0	0.3121	0.0	nan	0.7610	0.8703	0.5177	0.7369	0.3866	nan	0.4110	0.5213	0.0	0.8051	0.0	0.0	nan	0.0	0.3223	0.0	0.0	0.7368	0.0	0.3795	0.3303	0.0	nan	0.0	0.3181	0.0	0.0	0.8558	0.7279	0.9245	0.0	0.0	0.2057	0.0
0.3566	16.0	3200	0.5746	0.3154	0.3831	0.8543	nan	0.9156	0.9537	0.5807	0.8263	0.4642	nan	0.5228	0.8130	0.0	0.9300	0.0	0.0	nan	0.0	0.5625	0.0	0.0	0.8697	0.0	0.5473	0.3708	0.0	nan	0.0	0.4250	0.0	0.0	0.9320	0.8671	0.9687	0.0	0.0	0.3279	0.0	nan	0.7622	0.8696	0.5476	0.7333	0.3773	nan	0.4062	0.5234	0.0	0.8021	0.0	0.0	nan	0.0	0.3295	0.0	0.0	0.7271	0.0	0.3621	0.3111	0.0	nan	0.0	0.3157	0.0	0.0	0.8569	0.7294	0.9246	0.0	0.0	0.1997	0.0
0.3486	17.0	3400	0.5716	0.3168	0.3810	0.8550	nan	0.9087	0.9592	0.5998	0.7778	0.4799	nan	0.5562	0.7959	0.0	0.9295	0.0	0.0	nan	0.0	0.4951	0.0	0.0	0.8892	0.0	0.5531	0.3860	0.0	nan	0.0	0.4274	0.0	0.0	0.9295	0.8539	0.9663	0.0	0.0	0.3037	0.0	nan	0.7539	0.8708	0.5570	0.7185	0.3903	nan	0.4183	0.5347	0.0	0.7991	0.0	0.0	nan	0.0	0.3381	0.0	0.0	0.7322	0.0	0.3614	0.3128	0.0	nan	0.0	0.3210	0.0	0.0	0.8602	0.7322	0.9260	0.0	0.0	0.1958	0.0
0.2541	18.0	3600	0.5641	0.3185	0.3816	0.8573	nan	0.9128	0.9560	0.6054	0.8210	0.4610	nan	0.5325	0.7977	0.0	0.9235	0.0	0.0	nan	0.0	0.5042	0.0	0.0	0.9042	0.0	0.5403	0.3783	0.0	nan	0.0	0.4368	0.0	0.0	0.9330	0.8523	0.9728	0.0	0.0	0.2982	0.0	nan	0.7718	0.8707	0.5635	0.7389	0.3730	nan	0.4092	0.5344	0.0	0.8080	0.0	0.0	nan	0.0	0.3504	0.0	0.0	0.7379	0.0	0.3729	0.3107	0.0	nan	0.0	0.3226	0.0	0.0	0.8587	0.7271	0.9226	0.0	0.0	0.2016	0.0
0.3204	19.0	3800	0.5781	0.3170	0.3798	0.8554	nan	0.9236	0.9609	0.5748	0.7706	0.4581	nan	0.5274	0.7996	0.0	0.9291	0.0	0.0	nan	0.0	0.5223	0.0	0.0	0.9019	0.0	0.5425	0.3743	0.0	nan	0.0	0.4318	0.0	0.0	0.9265	0.8595	0.9685	0.0	0.0	0.3016	0.0	nan	0.7477	0.8692	0.5451	0.7127	0.3767	nan	0.4137	0.5304	0.0	0.8061	0.0	0.0	nan	0.0	0.3493	0.0	0.0	0.7376	0.0	0.3776	0.3140	0.0	nan	0.0	0.3249	0.0	0.0	0.8609	0.7330	0.9252	0.0	0.0	0.2027	0.0
0.3648	20.0	4000	0.5669	0.3190	0.3821	0.8574	nan	0.9199	0.9566	0.5855	0.8187	0.4712	nan	0.5293	0.7962	0.0	0.9245	0.0	0.0	nan	0.0	0.5123	0.0	0.0	0.8912	0.0	0.5405	0.3863	0.0	nan	0.0	0.4414	0.0	0.0	0.9331	0.8636	0.9713	0.0000	0.0	0.3037	0.0	nan	0.7635	0.8715	0.5513	0.7441	0.3799	nan	0.4143	0.5353	0.0	0.8080	0.0	0.0	nan	0.0	0.3478	0.0	0.0	0.7370	0.0	0.3749	0.3203	0.0	nan	0.0	0.3284	0.0	0.0	0.8586	0.7283	0.9243	0.0000	0.0	0.2014	0.0

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0